Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that denote directional movement or pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uest
    -0.17
    IVED
    -0.16
     aside
    -0.15
    asa
    -0.14
     QuáºŃn
    -0.14
    uno
    -0.14
    oÅĪ
    -0.14
    -lfs
    -0.14
    -urlencoded
    -0.14
    bnb
    -0.14
    POSITIVE LOGITS
     destinations
    0.18
    лÑı
    0.17
     destination
    0.17
     nowhere
    0.17
    ÃŃda
    0.15
    ymax
    0.14
     obliv
    0.14
     ÙĨÙĤ
    0.14
     distant
    0.14
    /from
    0.14
    Act Density 0.167%

    No Known Activations